A Novel Combating Email Spam and Phishing Classifier Using Intelligent Multinomial Naive Bayes Classification

Abstract

Since email is still one of the most popular means of communication, it is frequently the subject of phishing and spam attacks, which put people's and organisations' security at grave danger. Conventional detection methods, such signature-based filtering and blacklisting, frequently fall short of spotting dynamic phishing patterns and transient harmful links. This work suggests an automated email spam classification system using the Multinomial Naive Bayes method to overcome these drawbacks. The program successfully differentiates between spam and authentic (ham) emails by using word frequency analysis and textual feature extraction. Multinomial Naive Bayes exhibits dependable results in identifying spam content because of its simplicity, effectiveness, and solid probabilistic base. The suggested method provides a scalable and efficient way to improve email security and reduce cyber threats associated with phishing.